Check patentability & draft patents in minutes with Patsnap Eureka AI!

Method for realizing intelligent student service based on artificial intelligence BERT model

A model implementation and artificial intelligence technology, applied in the field of intelligent student services, can solve the problems that the student service system does not have intelligent answering functions, is not intelligent enough, and intelligent, and achieves the effect of intelligent semantic analysis, more semantic analysis, and increased concurrent carrying capacity

Pending Publication Date: 2022-02-18
弘成科技发展有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a method for realizing intelligent student service based on the artificial intelligence BERT model, so as to solve the problem that the existing student service system does not have the intelligent answer function and even if there are similar tools, it is not intelligent enough.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0024] A method of realizing intelligent student services based on the artificial intelligence BERT model, including collecting information to form a set; labeling the formed set to form a category, and then entering the labeled corpus information into the database; and then building an AI model based on BERT+BM2; After building the AI ​​model, build the AI ​​back-end service and realize the middle-end service through java, and the front-end program can call the middle-end java service; after the above system is built, interact, after the interaction is completed, collect the user's satisfaction with this service, In order to tune the model or continuously supplement the problem.

[0025] For routine questions in the learning process of students, such as WeChat official account, WeChat applet, APP and other applications, intelligent answering and intelligent reply can be realized; it mainly involves two pieces of content, one part is intelligent answering of routine general que...

specific Embodiment 2

[0028] This embodiment further explains information collection on the basis of specific embodiment 1. The information collection is used to form a collection, including collecting routine questions and answer lists to form a corpus, and collecting service content related to the student learning process to form a service set.

[0029] The questions in the corpus are mainly aimed at tourists, such as the questions that students will have when they pass the admissions process, and the service-focused questions are mainly aimed at the learning services of current students, extracting possible questions from students to targeted questions related to their own student progress, majors, etc. Serve.

specific Embodiment 3

[0031] This embodiment is based on the specific embodiment 2 to further explain the further processing method of the formed set. The formation of the category by labeling the formed set is specifically represented by labeling the formed question set and service set. Issue class or service class.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method for realizing intelligent student service based on an artificial intelligence BERT model. The method comprises the following steps: collecting information to form a set; labelling the formed set to form a category, and then inputting the labeled corpus information into a database; then, constructing an AI model based on BERT + BM2; after the AI model is constructed, establishing an AI back-end service, realizing a middle-end service through java, and a front-end program can call the middle-end java service; after the system is built, performing interaction, and after interaction is completed, collecting the satisfaction degree of a user for the service so as to adjust and optimize a model or continuously supplement problems. The problems that an existing student service system does not have an intelligent answering function and is not intelligent enough even if similar tools exist are solved.

Description

technical field [0001] The invention relates to the field of intelligent student services, in particular to a method for realizing intelligent student services based on an artificial intelligence BERT model. Background technique [0002] With the vigorous development of online education, especially the popularization of online education and adult education informatization, more and more students have adopted distance learning methods to complete course learning and examinations. Students may feel the convenience and advantages brought by informatization and intelligence. There may also be some problems encountered in the process of enrollment, payment, and learning. The traditional method may still be sent to the teacher by phone, email, QQ, WeChat, etc., or asked by classmates. This way of manually answering questions, Affected by the busyness of commuting and consultation, sometimes it may not be possible to get feedback on problems in a timely manner; on the other hand, i...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/332G06F40/216G06F40/30G10L15/22
CPCG06F16/3329G06F40/30G10L15/22G06F40/216
Inventor 李旭旻
Owner 弘成科技发展有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More